Journal of Hepatocellular Carcinoma最新文献

{"title":"Radiomics and Deep Learning as Important Techniques of Artificial Intelligence - Diagnosing Perspectives in Cytokeratin 19 Positive Hepatocellular Carcinoma.","authors":"Fei Wang, Chunyue Yan, Xinlan Huang, Jiqiang He, Ming Yang, Deqiang Xian","doi":"10.2147/JHC.S526887","DOIUrl":"10.2147/JHC.S526887","url":null,"abstract":"<p><strong>Background: </strong>Currently, there are inconsistencies among different studies on preoperative prediction of Cytokeratin 19 (CK19) expression in HCC using traditional imaging, radiomics, and deep learning. We aimed to systematically analyze and compare the performance of non-invasive methods for predicting CK19-positive HCC, thereby providing insights for the stratified management of HCC patients.</p><p><strong>Methods: </strong>A comprehensive literature search was conducted in PubMed, EMBASE, Web of Science, and the Cochrane Library from inception to February 2025. Two investigators independently screened and extracted data based on inclusion and exclusion criteria. Eligible studies were included, and key findings were summarized in tables to provide a clear overview.</p><p><strong>Results: </strong>Ultimately, 22 studies involving 3395 HCC patients were included. 72.7% (16/22) focused on traditional imaging, 36.4% (8/22) on radiomics, 9.1% (2/22) on deep learning, and 54.5% (12/22) on combined models. The magnetic resonance imaging was the most commonly used imaging modality (19/22), and over half of the studies (12/22) were published between 2022 and 2025. Moreover, 27.3% (6/22) were multicenter studies, 36.4% (8/22) included a validation set, and only 13.6% (3/22) were prospective. The area under the curve (AUC) range of using clinical and traditional imaging was 0.560 to 0.917. The AUC ranges of radiomics were 0.648 to 0.951, and the AUC ranges of deep learning were 0.718 to 0.820. Notably, the AUC ranges of combined models of clinical, imaging, radiomics and deep learning were 0.614 to 0.995. Nevertheless, the multicenter external data were limited, with only 13.6% (3/22) incorporating validation.</p><p><strong>Conclusion: </strong>The combined model integrating traditional imaging, radiomics and deep learning achieves excellent potential and performance for predicting CK19 in HCC. Based on current limitations, future research should focus on building an easy-to-use dynamic online tool, combining multicenter-multimodal imaging and advanced deep learning approaches to enhance the accuracy and robustness of model predictions.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1129-1140"},"PeriodicalIF":4.2,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12149279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144266419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness and Safety of Systemic Therapy and Stereotactic Body Radiotherapy in Oligoprogressive and Oligometastatic Hepatocellular Carcinoma.","authors":"Zhuo Song, Xuan Zheng, Hongzhi Wang, Dezuo Dong, Xianggao Zhu, Jianhao Geng, Shuai Li, Maxiaowei Song, Rongxu Du, Yangzi Zhang, Zhiyan Liu, Yong Cai, Yongheng Li, Weihu Wang","doi":"10.2147/JHC.S519770","DOIUrl":"10.2147/JHC.S519770","url":null,"abstract":"<p><strong>Purpose: </strong>This study explored the efficacy and safety of combining systemic therapy with stereotactic body radiotherapy (SBRT) for oligoprogressive (OP) and oligometastatic (OM) hepatocellular carcinoma (HCC).</p><p><strong>Patients and methods: </strong>From January 2017 to June 2023, 37 HCC patients (28 OP, 9 OM) receiving systemic therapy and SBRT were identified. OP is defined as up to 5 progressive lesions with others stable after systemic therapy and OM as newly identified metastatic disease with up to 5 metastatic lesions. SBRT was delivered in fractions of 5 Gy or more to all lesions. Clinical outcomes and toxicity were evaluated.</p><p><strong>Results: </strong>The median follow-up was 32.8 months. The objective response rates (ORRs) were 47.2%, 44.4%, and 55.5% for overall, OP, and OM cohorts. SBRT treated 48 OP and 17 OM lesions, achieving an ORR of 64.7%. For overall, OP, and OM cohorts, the 2-year local failure rates were 3.0%, 4.0%, and 0%, with median progression-free survival (PFS) of 11.2, 11.2, and 10.2 months, and median overall survival (OS) of 34.9 months, 32.6 months, and not reached (NR), respectively. In the OP cohort, 12 patients switched to next-line systemic therapy (OP-N) and 16 remained on current therapy (OP-C). Median PFS and OS were 11.6 months and NR for OP-N versus 16.5 months and 32.6 months for OP-C (P=0.89 and 0.47). Grade 3 acute and late treatment-related adverse events occurred in 40.5% and 5.4% of patients.</p><p><strong>Conclusion: </strong>Systemic therapy combined with SBRT was effective and safe for OP and OM HCC. SBRT may delay next-line systemic therapy by blocking OP.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1097-1110"},"PeriodicalIF":4.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12136078/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144225688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Resistance and Survival of HCC Patients Post-HAIC: Based on Shapley Additive exPlanations and Machine Learning.","authors":"Fan Yao, Jianliang Miao, Bing Quan, Jinghuan Li, Bei Tang, Shenxin Lu, Xin Yin","doi":"10.2147/JHC.S523806","DOIUrl":"10.2147/JHC.S523806","url":null,"abstract":"<p><strong>Purpose: </strong>To establish prediction models using Shapley Additive exPlanations (SHAP) and multiple machine learning (ML) algorithms to identify clinical features influencing hepatic arterial infusion chemotherapy (HAIC) resistance and survival in patients with hepatocellular carcinoma (HCC).</p><p><strong>Patients and methods: </strong>We recruited 286 patients with unresectable HCC who underwent HAIC. Patients were divided into training and validation datasets (7:3 ratio). eXtreme Gradient Boosting (XGBoost) was used to build the preliminary resistance prediction model. The SHAP values explained the importance of the clinical features. Recursive Feature Elimination with Cross-Validation (RFECV) was used to select the optimum number of features. Seven ML methods were used to construct further resistance prediction models, and ten ML algorithms were employed to establish the survival prognosis models.</p><p><strong>Results: </strong>The areas under the curve (AUC) of the XGBoost model were 1.000 and 0.812 for the training and validation groups, respectively. SHAP identified 27 of the 38 clinical features affecting resistance, with pre-HAIC treatment being the main factor. RFECV showed the best model performance with six features (pre-HAIC treatment, tumor size, HBV DNA, alkaline phosphatase (AKP), prothrombin time (PT), and portal vein tumor thrombosis (PVTT)). Random Forest had the best performance among the seven ML algorithms (AUC=0.935 for training, AUC=0.876 for validation). The combination of Stepcox [forward] and Gradient Boosting Machine was the best for predicting survival (AUC=0.98 in training, AUC=0.83 in validation). Based on the above clinical characteristics, patients were categorized into high-risk and low-risk groups based on the median risk score, and it was found that these characteristics also performed well in the prognostic model for predicting the survival of patients with HCC.</p><p><strong>Conclusion: </strong>Pre-HAIC treatment, tumor size, HBV DNA, AKP, PT, and PVTT are effective predictors of post-HAIC resistance and survival in patients with unresectable advanced HCC.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1111-1128"},"PeriodicalIF":4.2,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12140075/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144234330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intratumoral and Peritumoral Radiomics Based on DCE-MRI for Prediction of Microvascular Invasion Grading in Solitary Hepatocellular Carcinoma (≤3 cm).","authors":"Yinqiao Li, Helin Li, Yayuan Feng, Lun Lu, Juan Zhang, Ningyang Jia","doi":"10.2147/JHC.S519578","DOIUrl":"10.2147/JHC.S519578","url":null,"abstract":"<p><strong>Purpose: </strong>To explore the application value of clinical indicators, radiological features, and magnetic resonance imaging (MRI) radiomics to predict the grading of MVI in nodular hepatocellular carcinoma (≤3cm).</p><p><strong>Methods: </strong>A total of 131 patients with hepatocellular carcinoma (HCC) and confirmed microvascular invasion (MVI) who underwent surgical resection between January 2016 and December 2022 were retrospectively analyzed. A clinical-radiological (CR) model was constructed using independent risk factors identified by logistic regression. Radiomics models based on MRI (arterial phase, portal venous phase, delayed phase) across various regions (AVDP_intra, AVDP_{intra+peri3mm}, AVDP_{intra+peri5mm}, AVDP_{intra+peri10mm}) were developed using the Logistic Regression (LR) classifiers. The optimal radiomics model was subsequently integrated with the CR model to construct a combined clinical-radiological-radiomics (CRR) model. Model performance was assessed using the area under the curve (AUC).</p><p><strong>Results: </strong>Non-smooth margin and intratumoral artery were risk factors for MVI grading. The combined CRR model demonstrated the best predictive performance, with AUCs of 0.907 and 0.917 in the training and testing sets, respectively. Compared with the CR model alone, the CRR model showed a statistically significant improvement (p = 0.008, DeLong test).</p><p><strong>Conclusion: </strong>The AVDP_{intra+peri3mm} model based on MRI radiomics demonstrates good predictive performance in predicting MVI grading in HCC (≤3cm). Combining features from the CR model with those of the AVDP_{intra+peri3mm} model to construct the CRR model further enhances the prediction of MVI grading.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1083-1095"},"PeriodicalIF":4.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12132667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spleen Volume Dynamics and Survival Outcomes in HCC Patients Undergoing Immune Checkpoint Inhibitors: A Retrospective Analysis.","authors":"Xiaona Fu, Shanshan Jiang, Yi Li, Yusheng Guo, Bingxin Gong, Jie Lou, Yanlin Li, Sichen Wang, Yuxin Sun, Yi Ren, Quan Chen, Lian Yang","doi":"10.2147/JHC.S524483","DOIUrl":"10.2147/JHC.S524483","url":null,"abstract":"<p><strong>Purpose: </strong>The spleen serves as an important immune organ which influences the anti-tumor immune response by modulating the immune microenvironment. This study investigated the prognostic impact of spleen volume (SV) on the survival in hepatocellular carcinoma (HCC) patients receiving immune checkpoint inhibitors (ICIs).</p><p><strong>Patients and methods: </strong>This retrospective study included 224 HCC patients treated with ICIs, categorized into Higher and Lower SV groups by median SV and further into SV increased and Non-SV increased groups based on changes in SV at 3 months after ICIs. Kaplan-Meier curves and Cox regression models were used to evaluate the influence of SV and clinical indicators on progression-free survival (PFS) and overall survival (OS). Independent prognostic factors identified via multivariate analysis were incorporated into nomograms, with their accuracy assessed using concordance index (C-index), time-dependent receiver operating characteristic (ROC) and calibration curves. Restricted cubic spline (RCS) analysis was conducted to assess the relationship between baseline SV and survival.</p><p><strong>Results: </strong>The Higher SV and SV increased groups demonstrated shorter PFS and OS compared to the Lower SV and Non-SV increased groups, respectively. These results were consistent with different regimens in the Child A. The C-index of nomogram for PFS were 0.700 (0.678-0.721) and OS 0.733(0.709-0.757). The ROC and calibration curves confirmed robust discrimination and predictive accuracy of models. RCS analysis revealed a nonlinear association between baseline SV and survival risk, providing a more comprehensive overview of SV in relation to survival in HCC patients treated with ICIs.</p><p><strong>Conclusion: </strong>The baseline SV and its relative change at three months after treatment are expected to become routine imaging makers for predicting survival in HCC patients receiving ICIs, which consequently contributes to their clinical management.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1069-1082"},"PeriodicalIF":4.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12132512/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Primary Prophylaxis for High-Risk Varices in Patients with Hepatocellular Carcinoma and Portal Vein Tumor Thrombus Delayed Hepatic Decompensation: A Retrospective, Propensity Score Matching Study.","authors":"Yu-Jen Chen, Ming-Chih Hou, Tsung-Chieh Yang, Pei-Chang Lee, Hsiao-Sheng Lu, Hui-Chun Huang, Yi-Hsiang Huang, Jiing-Chyuan Luo","doi":"10.2147/JHC.S520318","DOIUrl":"10.2147/JHC.S520318","url":null,"abstract":"<p><strong>Background and aims: </strong>The prevalence of clinically significant portal hypertension (CSPH) is high in patients with hepatocellular carcinoma (HCC) and portal vein tumor thrombus (PVTT). There was no evidence of whether primary prophylaxis is beneficial in reducing hepatic decompensation in these patients.</p><p><strong>Methods: </strong>Clinical records of 445 patients with pathology or radiology-confirmed HCC and PVTT from January 2013 to December 2022 were reviewed, 142 patients having concurrent high-risk varices (HRV) without hepatic decompensation were enrolled. Patients were divided into the prophylaxis group and non-prophylaxis group. Propensity score matching was used for group comparison. The primary endpoint was decompensation-free survival (DFS), and the secondary endpoints were the incidence of esophageal variceal bleeding (EVB) and overall survival (OS).</p><p><strong>Results: </strong>The incidence of EVB was higher in the non-prophylaxis group than in the prophylaxis group (46.8% VS 21%, p = 0.001). DFS was longer in the prophylaxis group than in the non-prophylaxis group (84 days vs 66 days, p = 0.009). There was no difference in OS between two groups. In multivariate analysis, primary prophylaxis was associated with longer DFS (HR 0.806, p = 0.017); Immunotherapy (IO) was associated with longer DFS and OS; Barcelona Clinic Liver Cancer (BCLC) stage D was associated with shorter DFS and OS.</p><p><strong>Conclusion: </strong>Primary prophylaxis delays hepatic decompensation in HCC patients with PVTT. The incidence of EVB was also lower in the prophylaxis group, particularly in those treated with NSBB. First-line IO treatment is independently associated with better DFS and OS.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1057-1067"},"PeriodicalIF":4.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12127523/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transarterial Chemoembolization, Molecular Targeted Treatments, and Programmed Death-(Ligand)1 Inhibitors, for Hepatocellular Carcinoma with Lung Metastasis: A Retrospective Cohort Study.","authors":"Junjie Lu, Xiang Chen, Yongfa Liu, Yi Ding, Bo Li, Jin Yang, Wei Peng, Xiaoli Yang","doi":"10.2147/JHC.S509120","DOIUrl":"10.2147/JHC.S509120","url":null,"abstract":"<p><strong>Background: </strong>Treatment options for patients with hepatocellular carcinoma (HCC) and lung metastases are diverse, requiring a personalized approach. Current CNLC guidelines recommend systemic therapy and focal radiation, emphasizing the roles of molecular targeted treatments (MTT) and programmed death-(ligand)1 (PD-[L]1) inhibitors. However, the efficacy of combining TACE with these treatments remains uncertain.</p><p><strong>Purpose: </strong>To compare the efficacy and adverse reactions of TACE combined with MTT and PD-(L)1 versus MTT and (PD-[L]1) in patients with HCC and lung metastasis.</p><p><strong>Materials and methods: </strong>We retrospectively analyzed data from patients treated between January 2019 and May 2024 at the Affiliated Hospital of Southwest Medical University and West China Hospital of Sichuan University. Stabilized inverse probability weighting was employed to reduce bias. The primary outcome was overall survival (OS); secondary outcomes included progression-free survival (PFS) and objective response rate (ORR).</p><p><strong>Results: </strong>Among 167 patients, 141 received TACE, MTT, and PD-(L)1, while 26 received MTT and PD-(L)1. The median follow-up times were 28 and 29 months, respectively. After weighting, baseline characteristics were well balanced. The median OS was significantly longer in the TACE group (15 months) compared to the MTT group (8 months; p=0.023), and PFS was also longer (8 months vs 5 months; p=0.038). For liver lesions, ORR was 42.6% in the TACE group and 46.2% in the MTT group (p=0.73); for lung lesions, ORR was 26.2% and 19.2%, respectively (p=0.449). Safety profiles were similar, except for a higher incidence of rash in the MTT group.</p><p><strong>Conclusion: </strong>TACE combined with MTT and PD-(L)1 demonstrated better outcomes for patients with liver cancer and lung metastases compared to MTT and PD-(L)1 alone, without increasing complication rates, suggesting a promising first-line treatment option.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1031-1041"},"PeriodicalIF":4.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108955/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144159603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adjuvant Lenvatinib for High-Risk CNLC IIb/IIIa Hepatocellular Carcinoma After Curative Hepatectomy: A Prospective Exploratory Study.","authors":"Hui-Chuan Sun, Zhi-Yong Huang, Tianfu Wen, Lianxin Liu, Xiao-Dong Zhu, Erlei Zhang, Chuan Li, Xiaoyun Zhang, Jiabei Wang, Jia Fan, Jian Zhou","doi":"10.2147/JHC.S516478","DOIUrl":"10.2147/JHC.S516478","url":null,"abstract":"<p><strong>Objective: </strong>The risk of hepatocellular carcinoma (HCC) recurrence following surgical resection remains high, approaching 50%-70% at 5 years, with the highest risk occurring in the first year after resection. This study aimed to evaluate the efficacy and safety of lenvatinib as adjuvant therapy for HCC.</p><p><strong>Methods: </strong>In this open-label, single-arm, prospective, multicenter Phase II clinical study, a total of 51 hCC patients with China Liver Cancer (CNLC) stage IIb/IIIa (ie tumor number ≥ 4 or vascular invasion, equivalent to BCLC B/C) who underwent R0 resection 4-6 weeks after curative surgery were enrolled. Patients received lenvatinib for up to 12 months, at a dose of 8 mg/day for body weight < 60 kg, or 12 mg/day for ≥ 60 kg. Patients were followed up every 2 months for a median of 24.1 months.</p><p><strong>Results: </strong>The median recurrence-free survival (RFS) was 16.1 months, with a 12-month RFS rate of 60.4%, exceeding the historical rate of under 50% in similar high-risk populations. The 12-month overall survival (OS) rate was 93.6%, while median OS was not reached. Treatment-related adverse events (TRAEs) occurred in 88.0% of patients, with ≥ grade 3 TRAEs in 14.0%, including thrombocytopenia and proteinuria in 6.0% of patients each, and leukopenia, neutropenia, elevated aspartate aminotransferase, and elevated alanine aminotransferase in 2.0% of patients each. AEs leading to the interruption of lenvatinib occurred in 6.0% of patients, and dose reduction was required in 18% of patients. No deaths were observed.</p><p><strong>Conclusion: </strong>Lenvatinib may be an effective adjuvant therapy for patients with CNLC stage IIb/IIIa HCC after R0 hepatectomy. However, the findings are limited by the single-arm design and small patient cohort, necessitating larger randomized controlled trials for validation.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1043-1056"},"PeriodicalIF":4.2,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105637/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144150733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combination of Hepatic Arterial Infusion Chemotherapy with Tyrosine Kinase Inhibitor Provides Better Survival in Advanced Hepatocellular Carcinoma Patients.","authors":"Chung-Wei Liu, Po-Ting Lin, Wei Teng, Wei-Ting Chen, Chung-Wei Su, Yi-Chung Hsieh, Chen-Chun Lin, Chun-Yen Lin, Shi-Ming Lin","doi":"10.2147/JHC.S502922","DOIUrl":"10.2147/JHC.S502922","url":null,"abstract":"<p><strong>Introduction: </strong>Hepatic arterial infusion chemotherapy (HAIC) and tyrosine kinase inhibitors (TKI) are widely used to treat unresectable hepatocellular carcinoma (HCC). This study investigated the benefits of combining TKI and HAIC in these patients.</p><p><strong>Methods: </strong>We retrospectively analyzed patients with unresectable HCC treated at Linkou Chang Gung Memorial Hospital between March 2009 and February 2022. The patients were categorized into two groups: HAIC combined with TKI therapy and HAIC alone. Kaplan-Meier analysis, Cox proportional hazards models, and propensity score matching were applied.</p><p><strong>Results: </strong>Among 130 patients, the combination therapy group showed significantly improved overall survival (OS) (20.2 versus 11.8 months, <i>p</i> = 0.000) and progression-free survival (PFS) (8.2 versus 3.6 months, <i>p</i> = 0.011) compared to the HAIC-only group. These advantages persisted after propensity score matching with improved OS (20.2 vs 12.9 months, <i>p</i> = 0.001) and extrahepatic PFS (12.4 vs 5.5 months, <i>p</i> = 0.008). Combination therapy improved PFS in the stage IV portal vein thrombosis (PVT) subgroup. TKI combination therapy, more than nine HAIC cycles, and post-HAIC transarterial chemoembolization (TACE) were independent predictors of improved OS.</p><p><strong>Conclusion: </strong>Combining HAIC with TKI therapy improves survival outcomes compared to HAIC alone in patients with unresectable HCC, especially in cases with extrahepatic spread and PVT. Sequential TACE following HAIC therapy further enhances survival benefits.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"1017-1029"},"PeriodicalIF":4.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12103852/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144142713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiomics of Dynamic Contrast-Enhanced MRI for Predicting Radiation-Induced Hepatic Toxicity After Intensity Modulated Radiotherapy for Hepatocellular Carcinoma: A Machine Learning Predictive Model Based on the SHAP Methodology.","authors":"Fushuang Liu, Lijun Chen, Qiaoyuan Wu, Liqing Li, Jizhou Li, Tingshi Su, Jianxu Li, Shixiong Liang, Liping Qing","doi":"10.2147/JHC.S523448","DOIUrl":"10.2147/JHC.S523448","url":null,"abstract":"<p><strong>Objective: </strong>To develop an interpretable machine learning (ML) model using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic data, dosimetric parameters, and clinical data for predicting radiation-induced hepatic toxicity (RIHT) in patients with hepatocellular carcinoma (HCC) following intensity-modulated radiation therapy (IMRT).</p><p><strong>Methods: </strong>A retrospective analysis of 150 HCC patients was performed, with a 7:3 ratio used to divide the data into training and validation cohorts. Radiomic features from the original MRI sequences and Delta-radiomic features were extracted. Seven ML models based on radiomics were developed: logistic regression (LR), random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), adaptive boosting (AdaBoost), decision tree (DT), and artificial neural network (ANN). The predictive performance of the models was evaluated using receiver operating characteristic (ROC) curve analysis and calibration curves. Shapley additive explanations (SHAP) were employed to interpret the contribution of each variable and its risk threshold.</p><p><strong>Results: </strong>Original radiomic features and Delta-radiomic features were extracted from DCE-MRI images and filtered to generate Radiomics-scores and Delta-Radiomics-scores. These were then combined with independent risk factors (Body Mass Index (BMI), V5, and pre-Child-Pugh score(pre-CP)) identified through univariate and multivariate logistic regression and Spearman correlation analysis to construct the ML models. In the training cohort, the AUC values were 0.8651 for LR, 0.7004 for RF, 0.6349 for SVM, 0.6706 for XGBoost, 0.7341 for AdaBoost, 0.6806 for Decision Tree, and 0.6786 for ANN. The corresponding accuracies were 84.4%, 65.6%, 75.0%, 65.6%, 71.9%, 68.8%, and 71.9%, respectively. The validation cohort further confirmed the superiority of the LR model, which was selected as the optimal model. SHAP analysis revealed that Delta-radiomics made a substantial positive contribution to the model.</p><p><strong>Conclusion: </strong>The interpretable ML model based on radiomics provides a non-invasive tool for predicting RIHT in patients with HCC, demonstrating satisfactory discriminative performance.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"12 ","pages":"999-1015"},"PeriodicalIF":4.2,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12095435/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}